Search

This paper presents a Multimodal Ambient Context-enriched Intelligence Platform (MACeIP) for Smart Cities, a comprehensive system designed to enhance urban management and citizen engagement. Our platform integrates advanced technologies, including Internet of Things (IoT) sensors, edge and cloud computing, and Multimodal AI, to create a responsive and intelligent urban ecosystem. Key components include Interactive Hubs for citizen interaction, an extensive IoT sensor network, intelligent public asset management, a pedestrian monitoring system, a City Planning Portal, and a Cloud Computing System. We demonstrate the prototype of MACeIP in several cities, focusing on Fredericton, New Brunswick. This work contributes to innovative city development by offering a scalable, efficient, and user-centric approach to urban intelligence and management., Comment: 4 pages, 6 figures, IEEE/IEIE ICCE-Asia 2024

Letters of recommendation from school counselors are required to apply to many selective colleges and universities. Still, relatively little is known about how this non-standardized component may affect equity in admissions. We use cutting-edge natural language processing techniques to algorithmically analyze a national dataset of over 600,000 student applications and counselor recommendation letters submitted via the Common App platform. We examine how the length and topical content of letters (e.g., sentences about Personal Qualities, Athletics, Intellectual Promise, etc.) relate to student self-identified race/ethnicity, sex, and proxies for socioeconomic status. Paired with regression analyses, we explore whether demographic differences in letter characteristics persist when accounting for additional student, school, and counselor characteristics, as well as among letters written by the same counselor and among students with comparably competitive standardized test scores. We ultimately find large and noteworthy naïve differences in letter length and content across nearly all demographic groups, many in alignment with known inequities (e.g., many more sentences about Athletics among White and higher-SES students, longer letters and more sentences on Personal Qualities for private school students). However, these differences vary drastically based on the exact controls and comparison groups included -- demonstrating that the ultimate implications of these letter differences for equity hinges on exactly how and when letters are used in admissions processes (e.g., among which groups of students are they used to "break ties"?). Findings do not point to a clear recommendation whether institutions should keep or discard letter requirements, but reflect the importance of reading letters and overall applications in the context of structural opportunity. We discuss additional implications and possible recommendations for college access and admissions policy/practice.

Large Language Models (LLMs), with gradually improving reading comprehension and reasoning capabilities, are being applied to a range of complex language tasks, including the automatic generation of language data for various purposes. However, research on applying LLMs for automatic data generation in low-resource languages like Vietnamese is still underdeveloped and lacks comprehensive evaluation. In this paper, we explore the use of LLMs for automatic data generation for the Vietnamese fact-checking task, which faces significant data limitations. Specifically, we focus on fact-checking data where claims are synthesized from multiple evidence sentences to assess the information synthesis capabilities of LLMs. We develop an automatic data construction process using simple prompt techniques on LLMs and explore several methods to improve the quality of the generated data. To evaluate the quality of the data generated by LLMs, we conduct both manual quality assessments and performance evaluations using language models. Experimental results and manual evaluations illustrate that while the quality of the generated data has significantly improved through fine-tuning techniques, LLMs still cannot match the data quality produced by humans.

Depth information plays a crucial role in autonomous systems for environmental perception and robot state estimation. With the rapid development of deep neural network technology, depth estimation has been extensively studied and shown potential for practical applications. However, in particularly challenging environments such as low-light and noisy underwater conditions, direct application of machine learning models may not yield the desired results. Therefore, in this paper, we present an approach to enhance underwater image quality to improve depth estimation effectiveness. First, underwater images are processed through methods such as color compensation, brightness equalization, and enhancement of contrast and sharpness of objects in the image. Next, we perform depth estimation using the Udepth model on the enhanced images. Finally, the results are evaluated and presented to verify the effectiveness and accuracy of the enhanced depth image quality approach for underwater robots., Comment: In The 26th National Conference on Electronics, Communications and Information Technology (REV-ECIT 2023), Hanoi, Vietnam, in Vietnamese language

Determining the difficulty of a text involves assessing various textual features that may impact the reader's text comprehension, yet current research in Vietnamese has only focused on statistical features. This paper introduces a new approach that integrates statistical and semantic approaches to assessing text readability. Our research utilized three distinct datasets: the Vietnamese Text Readability Dataset (ViRead), OneStopEnglish, and RACE, with the latter two translated into Vietnamese. Advanced semantic analysis methods were employed for the semantic aspect using state-of-the-art language models such as PhoBERT, ViDeBERTa, and ViBERT. In addition, statistical methods were incorporated to extract syntactic and lexical features of the text. We conducted experiments using various machine learning models, including Support Vector Machine (SVM), Random Forest, and Extra Trees and evaluated their performance using accuracy and F1 score metrics. Our results indicate that a joint approach that combines semantic and statistical features significantly enhances the accuracy of readability classification compared to using each method in isolation. The current study emphasizes the importance of considering both statistical and semantic aspects for a more accurate assessment of text difficulty in Vietnamese. This contribution to the field provides insights into the adaptability of advanced language models in the context of Vietnamese text readability. It lays the groundwork for future research in this area.

In this paper, we present a new space-time Petrov-Galerkin-like method. This method utilizes a mixed formulation of Tensor Train (TT) and Quantized Tensor Train (QTT), designed for the spectral element discretization (Q1-SEM) of the time-dependent convection-diffusion-reaction (CDR) equation. We reformulate the assembly process of the spectral element discretized CDR to enhance its compatibility with tensor operations and introduce a low-rank tensor structure for the spectral element operators. Recognizing the banded structure inherent in the spectral element framework's discrete operators, we further exploit the QTT format of the CDR to achieve greater speed and compression. Additionally, we present a comprehensive approach for integrating variable coefficients of CDR into the global discrete operators within the TT/QTT framework. The effectiveness of the proposed method, in terms of memory efficiency and computational complexity, is demonstrated through a series of numerical experiments, including a semi-linear example.

Federated Learning (FL) is a machine learning method for training with private data locally stored in distributed machines without gathering them into one place for central learning. Despite its promises, FL is prone to critical security risks. First, because FL depends on a central server to aggregate local training models, this is a single point of failure. The server might function maliciously. Second, due to its distributed nature, FL might encounter backdoor attacks by participating clients. They can poison the local model before submitting to the server. Either type of attack, on the server or the client side, would severely degrade learning accuracy. We propose FedBlock, a novel blockchain-based FL framework that addresses both of these security risks. FedBlock is uniquely desirable in that it involves only smart contract programming, thus deployable atop any blockchain network. Our framework is substantiated with a comprehensive evaluation study using real-world datasets. Its robustness against backdoor attacks is competitive with the literature of FL backdoor defense. The latter, however, does not address the server risk as we do., Comment: This paper has been accepted as a full paper for the IEEE Special Session Federated Learning on Big Data 2024 (IEEE BigData 2024)

A smooth diamond film, characterized by exceptional thermal conductivity, chemical stability, and optical properties, is highly suitable for a wide range of advanced applications. However, achieving uniform film quality presents a significant challenge for the CVD method due to non-uniformities in microwave distribution, electric fields, and the densities of reactive radicals during deposition processes involving $CH_4$ and $H_2$ precursors. Here, we systematically investigate the effects of microwave power and chamber pressure on surface roughness, crystalline quality, and the uniformity of diamond films. These findings provide valuable insights into the production of atomically smooth, high-quality diamond films with enhanced uniformity. By optimizing deposition parameters, we achieved a root-mean-square (RMS) surface roughness of 2 nm, comparable to high-pressure, high-temperature (HPHT) diamond substrates. Moreover, these conditions facilitated the formation of a pure single-crystal diamond phase, confirmed by the absence of contamination peaks in the Raman spectra

We present a benchmark for Planning And Reasoning Tasks in humaN-Robot collaboration (PARTNR) designed to study human-robot coordination in household activities. PARTNR tasks exhibit characteristics of everyday tasks, such as spatial, temporal, and heterogeneous agent capability constraints. We employ a semi-automated task generation pipeline using Large Language Models (LLMs), incorporating simulation in the loop for grounding and verification. PARTNR stands as the largest benchmark of its kind, comprising 100,000 natural language tasks, spanning 60 houses and 5,819 unique objects. We analyze state-of-the-art LLMs on PARTNR tasks, across the axes of planning, perception and skill execution. The analysis reveals significant limitations in SoTA models, such as poor coordination and failures in task tracking and recovery from errors. When LLMs are paired with real humans, they require 1.5x as many steps as two humans collaborating and 1.1x more steps than a single human, underscoring the potential for improvement in these models. We further show that fine-tuning smaller LLMs with planning data can achieve performance on par with models 9 times larger, while being 8.6x faster at inference. Overall, PARTNR highlights significant challenges facing collaborative embodied agents and aims to drive research in this direction., Comment: Alphabetical author order

Scatterometry is a tested method for measuring periodic semiconductor structures. Since the sizes of modern semiconductor structures have reached the nanoscale regime, the challenge is to determine the shape of periodic nanostructures with sub-nanometer accuracy. To increase the resolution of scatterometry, short-wavelength radiation like soft X-rays can be used. But, scatterometry with soft X-rays is an inverse problem whose solutions can be ambiguous and its sensitivity should be further increased to determine the shape of even more complicated periodic nanostructures made up of different materials. To achieve unique solutions with smaller uncertainties, scatterometry can leverage the excitation of low-Z materials with soft X-rays. Additional information from soft X-ray fluorescence analysis in a hybrid measurement approach can mitigate the problem of ambiguous solutions from soft X-ray scattering and could further decrease uncertainty. In this work, the hybrid approach is utilized to perform a comparison of solutions from the inverse problem and determine the actual solution over ambiguous solutions.

Predicting program behavior and reasoning about code execution remain significant challenges in software engineering, particularly for large language models (LLMs) designed for code analysis. While these models excel at understanding static syntax, they often struggle with dynamic reasoning tasks. We introduce Visual Coder, a simple yet effective approach that enhances code reasoning by integrating multimodal Chain-of-Thought (CoT) reasoning with a visual Control Flow Graph (CFG). By aligning code snippets with their corresponding CFGs, Visual Coder provides deeper insights into execution flow, enabling more accurate predictions of code behavior. Our experiments demonstrate that augmenting LLMs with visual CFGs significantly outperforms text-based CFG descriptions in code reasoning tasks. We address challenges in multimodal CoT integration through a reference mechanism, ensuring consistency between code and its execution path, thereby improving performance in program behavior prediction, error detection, and output generation.

Positron Emission Tomography (PET) and Computed Tomography (CT) are essential for diagnosing, staging, and monitoring various diseases, particularly cancer. Despite their importance, the use of PET/CT systems is limited by the necessity for radioactive materials, the scarcity of PET scanners, and the high cost associated with PET imaging. In contrast, CT scanners are more widely available and significantly less expensive. In response to these challenges, our study addresses the issue of generating PET images from CT images, aiming to reduce both the medical examination cost and the associated health risks for patients. Our contributions are twofold: First, we introduce a conditional diffusion model named CPDM, which, to our knowledge, is one of the initial attempts to employ a diffusion model for translating from CT to PET images. Second, we provide the largest CT-PET dataset to date, comprising 2,028,628 paired CT-PET images, which facilitates the training and evaluation of CT-to-PET translation models. For the CPDM model, we incorporate domain knowledge to develop two conditional maps: the Attention map and the Attenuation map. The former helps the diffusion process focus on areas of interest, while the latter improves PET data correction and ensures accurate diagnostic information. Experimental evaluations across various benchmarks demonstrate that CPDM surpasses existing methods in generating high-quality PET images in terms of multiple metrics. The source code and data samples are available at https://github.com/thanhhff/CPDM., Comment: IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2025

Thermoelectricity in telluride materials is often improved by replacing telluride with selenium in its crystal. Most work, however, focuses on bulk crystal and leaves the 2D thin films intact. In this paper, we optimize the fabrication of selenium-doped bismuth telluride (Bi$_2$Te$_{3-\rm{x}}$Se$_{\rm{x}}$) thin films using a 3-source thermal co-evaporation. Thermoelectric properties, including the Seebeck coefficient and electrical resistivity, are systematically characterized to evaluate the material's performance for thermoelectric applications near room temperature. The thin films were deposited under carefully controlled conditions, with the evaporation rates of bismuth, tellurium, and selenium precisely monitored to achieve the desired stoichiometry and crystalline phase. Finally, thermoelectricity in Bi$_2$Te$_{3-\rm{x}}$Se$_{\rm{x}}$ at the ultra-thin regime is investigated. We consistently obtain films with thickness near 30 nm with a Seebeck coefficient of 400 $\mu$V/K and a power factor of 1 mW/mK$^2$.

Establishing a unified theory of cognition has been a major goal of psychology. While there have been previous attempts to instantiate such theories by building computational models, we currently do not have one model that captures the human mind in its entirety. Here we introduce Centaur, a computational model that can predict and simulate human behavior in any experiment expressible in natural language. We derived Centaur by finetuning a state-of-the-art language model on a novel, large-scale data set called Psych-101. Psych-101 reaches an unprecedented scale, covering trial-by-trial data from over 60,000 participants performing over 10,000,000 choices in 160 experiments. Centaur not only captures the behavior of held-out participants better than existing cognitive models, but also generalizes to new cover stories, structural task modifications, and entirely new domains. Furthermore, we find that the model's internal representations become more aligned with human neural activity after finetuning. Taken together, Centaur is the first real candidate for a unified model of human cognition. We anticipate that it will have a disruptive impact on the cognitive sciences, challenging the existing paradigm for developing computational models.

In this paper we establish a conformal scattering theory for the defocusing semilinear wave equations on the Schwarzschild spacetime. We combine the energy and pointwise decay results of solutions obtained in \cite{Yang} and a Sobolev embedding on spacelike hypersurfaces to establish the energy estimates in two sides between the energy flux of solution through the Cauchy initial hypersurface $\Sigma_0=\left\{ t=0 \right\}$ and the one through the null conformal boundaries $\mathfrak{H}^+\cup \scri^+$ (resp. $\mathfrak{H}^-\cup \scri^-$). Combining these estimates and the well-posedness of Cauchy and Goursat problems for nonlinear wave equations we provide a bounded linear and locally Lipschitz scattering operator which maps the past scattering data to the future scattering data. Our results extend also the previous works \cite{BaSeZho1990,Jo2012,Jo2019} to an asymptotically flat spacetime such as Schwarzschild spacetime which is static and spherically symmetric., Comment: 17 pages

Accelerating end-to-end inference of transformer-based large language models (LLMs) is a critical component of AI services in datacenters. However, diverse compute characteristics of end-to-end LLM inference present challenges as previously proposed accelerators only address certain operations or stages (e.g., self-attention, generation stage, etc.). To address the unique challenges of accelerating end-to-end inference, we propose IANUS -- Integrated Accelerator based on NPU-PIM Unified Memory System. IANUS is a domain-specific system architecture that combines a Neural Processing Unit (NPU) with a Processing-in-Memory (PIM) to leverage both the NPU's high computation throughput and the PIM's high effective memory bandwidth. In particular, IANUS employs a unified main memory system where the PIM memory is used both for PIM operations and for NPU's main memory. The unified main memory system ensures that memory capacity is efficiently utilized and the movement of shared data between NPU and PIM is minimized. However, it introduces new challenges since normal memory accesses and PIM computations cannot be performed simultaneously. Thus, we propose novel PIM Access Scheduling that manages normal memory accesses and PIM computations through workload mapping and scheduling across the PIM and the NPU. Our detailed simulation evaluations show that IANUS improves the performance of GPT-2 by 6.2$\times$ and 3.2$\times$, on average, compared to the NVIDIA A100 GPU and the state-of-the-art accelerator. As a proof-of-concept, we develop a prototype of IANUS with a commercial PIM, NPU, and an FPGA-based PIM controller to demonstrate the feasibility of IANUS., Comment: Updated version of the paper accepted to ASPLOS 2024

In this paper, we introduce various covering number bounds for linear function classes, each subject to different constraints on input and matrix norms. These bounds are contingent on the rank of each class of matrices. We then apply these bounds to derive generalization errors for single layer transformers. Our results improve upon several existing generalization bounds in the literature and are independent of input sequence length, highlighting the advantages of employing low-rank matrices in transformer design. More specifically, our achieved generalisation error bound decays as $O(1/\sqrt{n})$ where $n$ is the sample length, which improves existing results in research literature of the order $O((\log n)/(\sqrt{n}))$. It also decays as $O(\log r_w)$ where $r_w$ is the rank of the combination of query and and key matrices., Comment: 20 pages

Service robots that work alongside humans in a shared environment need a navigation system that takes into account not only physical safety but also social norms for mutual cooperation. In this paper, we introduce a motion planning system that includes human states such as positions and velocities and their personal space for social-aware navigation. The system first extracts human positions from the LiDAR and the RGB-D camera. It then uses the Kalman filter to fuse that information for human state estimation. An asymmetric Gaussian function is then employed to model human personal space based on their states. This model is used as the input to the dynamic window approach algorithm to generate trajectories for the robot. Experiments show that the robot is able to navigate alongside humans in a dynamic environment while respecting their physical and psychological comfort., Comment: In Proceedings of 2024, the 7th International Conference on Control, Robotics and Informatics (ICCRI 2024)

It is well established that starting only with strong, projective quantum measurements, experiments can be designed to allow weak measurements, which lead to random walk between the possible final measurement outcomes. However, one can ask the reverse question: starting with only weak measurements, can all the results of standard strong measurements be recovered? Prior work has shown that some results can be, such as the Born rule for the probability of measurement outcomes as a function of wave intensity. In this paper we show that another crucial result can be reproduced by purely weak measurements, namely the collapse of a many-body, nonlocally entangled wave function on a time scale comparable to the characteristic time of a single, local measurement; for an entangled state of a single excitation among $N$ qubits, we find the collapse time scales as a double logarithm of $N$. This result affirms the self-consistency of the hypothesis that spontaneous weak measurements lie at the base of all physical measurements, independent of human observers., Comment: Fix typo in Appendix C

We apply the Effective Field Theory of Large Scale Structure (EFTofLSS) to non-standard models of dark matter with suppressed small-scale structure imprinted by early-time physics, here exemplified by interacting dark matter (IDM) coupled to standard model neutrinos, and cross-check that the EFTofLSS has no trouble replicating the real-space halo-halo power spectrum from N-body simulations. We perform forecasts for a DESI ELG-like experiment using the redshift-space power spectrum and find that, under very conservative priors on these parameters, the EFTofLSS is not expected to yield strong constraints on dark matter interactions. However, with a better understanding of the evolution of counterterms and stochastic terms with redshift, realistic IDM models could in principle be detected using the full-shape power spectrum analysis of such a spectroscopic galaxy survey., Comment: 23 pages, 7 figures

In this paper, we study the logarithmically regularized 2D Euler equations, which are derived by regularizing the Euler equation for the vorticity have been studied recently to get better understanding of the Euler equations. It was shown that the local well-posedness in the critical Sobolev space $H^1(\mathbb{R}^2)\cap H^{-1}(\mathbb{R}^2)$ can be derived for $\gamma>\dfrac{1}{2}$, and the strong ill-posedness in this borderline space was yielded by Kwon for $0\le\gamma\le\frac{1}{2}$. In this paper, we show that the local well-posedness of the logarithmically regularized 2D Euler equations can be achieved in the subcritical space $H^s(\mathbb{T}^2)$ with $s>2$ for $\gamma \ge 0$. Moreover, we prove that the data-to-solution map is not uniformly continuous in the Sobolev $H^s(\mathbb{T}^2)$ topology for any $s>2$.

Drawing inspiration from human learning behaviors, this work proposes a novel approach to mitigate catastrophic forgetting in Prompt-based Continual Learning models by exploiting the relationships between continuously emerging class data. We find that applying human habits of organizing and connecting information can serve as an efficient strategy when training deep learning models. Specifically, by building a hierarchical tree structure based on the expanding set of labels, we gain fresh insights into the data, identifying groups of similar classes could easily cause confusion. Additionally, we delve deeper into the hidden connections between classes by exploring the original pretrained model's behavior through an optimal transport-based approach. From these insights, we propose a novel regularization loss function that encourages models to focus more on challenging knowledge areas, thereby enhancing overall performance. Experimentally, our method demonstrated significant superiority over the most robust state-of-the-art models on various benchmarks.

We introduce Flat Hilbert Bayesian Inference (FHBI), an algorithm designed to enhance generalization in Bayesian inference. Our approach involves an iterative two-step procedure with an adversarial functional perturbation step and a functional descent step within the reproducing kernel Hilbert spaces. This methodology is supported by a theoretical analysis that extends previous findings on generalization ability from finite-dimensional Euclidean spaces to infinite-dimensional functional spaces. To evaluate the effectiveness of FHBI, we conduct comprehensive comparisons against seven baseline methods on the VTAB-1K benchmark, which encompasses 19 diverse datasets across various domains with diverse semantics. Empirical results demonstrate that FHBI consistently outperforms the baselines by notable margins, highlighting its practical efficacy.

Distributed acoustic sensing (DAS) technology leverages fiber optic cables to detect vibrations and acoustic events, which is a promising solution for real-time traffic monitoring. In this paper, we introduce a novel methodology for detecting and tracking vehicles using DAS data, focusing on real-time processing through edge computing. Our approach applies the Hough transform to detect straight-line segments in the spatiotemporal DAS data, corresponding to vehicles crossing the Astfjord bridge in Norway. These segments are further clustered using the Density-based spatial clustering of applications with noise (DBSCAN) algorithm to consolidate multiple detections of the same vehicle, reducing noise and improving accuracy. The proposed workflow effectively counts vehicles and estimates their speed with only tens of seconds latency, enabling real-time traffic monitoring on the edge. To validate the system, we compare DAS data with simultaneous video footage, achieving high accuracy in vehicle detection, including the distinction between cars and trucks based on signal strength and frequency content. Results show that the system is capable of processing large volumes of data efficiently. We also analyze vehicle speeds and traffic patterns, identifying temporal trends and variations in traffic flow. Real-time deployment on edge devices allows immediate analysis and visualization via cloud-based platforms. In addition to traffic monitoring, the method successfully detected structural responses in the bridge, highlighting its potential use in structural health monitoring., Comment: 11 pages, 17 figures

Federated Learning (FL) has emerged as a powerful paradigm for training machine learning models in a decentralized manner, preserving data privacy by keeping local data on clients. However, evaluating the robustness of these models against data perturbations on clients remains a significant challenge. Previous studies have assessed the effectiveness of models in centralized training based on certified accuracy, which guarantees that a certain percentage of the model's predictions will remain correct even if the input data is perturbed. However, the challenge of extending these evaluations to FL remains unresolved due to the unknown client's local data. To tackle this challenge, this study proposed a method named FedCert to take the first step toward evaluating the robustness of FL systems. The proposed method is designed to approximate the certified accuracy of a global model based on the certified accuracy and class distribution of each client. Additionally, considering the Non-Independent and Identically Distributed (Non-IID) nature of data in real-world scenarios, we introduce the client grouping algorithm to ensure reliable certified accuracy during the aggregation step of the approximation algorithm. Through theoretical analysis, we demonstrate the effectiveness of FedCert in assessing the robustness and reliability of FL systems. Moreover, experimental results on the CIFAR-10 and CIFAR-100 datasets under various scenarios show that FedCert consistently reduces the estimation error compared to baseline methods. This study offers a solution for evaluating the robustness of FL systems and lays the groundwork for future research to enhance the dependability of decentralized learning. The source code is available at https://github.com/thanhhff/FedCert/., Comment: The 22nd International Symposium on Network Computing and Applications (NCA 2024)

Spiking neural network (SNN) has emerged as a promising paradigm in computational neuroscience and artificial intelligence, offering advantages such as low energy consumption and small memory footprint. However, their practical adoption is constrained by several challenges, prominently among them being performance optimization. In this study, we present a novel approach to enhance the performance of SNN for images through a new coding method that exploits bit plane representation. Our proposed technique is designed to improve the accuracy of SNN without increasing model size. Also, we investigate the impacts of color models of the proposed coding process. Through extensive experimental validation, we demonstrate the effectiveness of our coding strategy in achieving performance gain across multiple datasets. To the best of our knowledge, this is the first research that considers bit planes and color models in the context of SNN. By leveraging the unique characteristics of bit planes, we hope to unlock new potentials in SNNs performance, potentially paving the way for more efficient and effective SNNs models in future researches and applications.

Unsupervised pre-training on vast amounts of graph data is critical in real-world applications wherein labeled data is limited, such as molecule properties prediction or materials science. Existing approaches pre-train models for specific graph domains, neglecting the inherent connections within networks. This limits their ability to transfer knowledge to various supervised tasks. In this work, we propose a novel pre-training strategy on graphs that focuses on modeling their multi-resolution structural information, allowing us to capture global information of the whole graph while preserving local structures around its nodes. We extend the work of Wave}let Positional Encoding (WavePE) from (Ngo et al., 2023) by pretraining a High-Order Permutation-Equivariant Autoencoder (HOPE-WavePE) to reconstruct node connectivities from their multi-resolution wavelet signals. Unlike existing positional encodings, our method is designed to become sensitivity to the input graph size in downstream tasks, which efficiently capture global structure on graphs. Since our approach relies solely on the graph structure, it is also domain-agnostic and adaptable to datasets from various domains, therefore paving the wave for developing general graph structure encoders and graph foundation models. We theoretically demonstrate that there exists a parametrization of such architecture that it can predict the output adjacency up to arbitrarily low error. We also evaluate HOPE-WavePE on graph-level prediction tasks of different areas and show its superiority compared to other methods.

Less than 10 meters deep, shallow landslides are rapidly moving and strongly dangerous slides. In the present work, the probabilistic distribution of the landslide detachment points within a valley is modelled as a spatial Poisson point process, whose intensity depends on geophysical predictors according to a generalized additive model. Modelling the intensity with a generalized additive model jointly allows to obtain good predictive performance and to preserve the interpretability of the effects of the geophysical predictors on the intensity of the process. We propose a novel workflow, based on Random Forests, to select the geophysical predictors entering the model for the intensity. In this context, the statistically significant effects are interpreted as activating or stabilizing factors for landslide detachment. In order to guarantee the transferability of the resulting model, training, validation, and test of the algorithm are performed on mutually disjoint valleys in the Alps of Lombardy (Italy). Finally, the uncertainty around the estimated intensity of the process is quantified via semiparametric bootstrap.

The ASVspoof 2021 benchmark, a widely-used evaluation framework for anti-spoofing, consists of two subsets: Logical Access (LA) and Deepfake (DF), featuring samples with varied coding characteristics and compression artifacts. Notably, the current state-of-the-art (SOTA) system boasts impressive performance, achieving an Equal Error Rate (EER) of 0.87% on the LA subset and 2.58% on the DF. However, benchmark accuracy is no guarantee of robustness in real-world scenarios. This paper investigates the effectiveness of utilizing room impulse responses (RIRs) to enhance fake speech and increase their likelihood of evading fake speech detection systems. Our findings reveal that this simple approach significantly improves the evasion rate, doubling the SOTA system's EER. To counter this type of attack, We augmented training data with a large-scale synthetic/simulated RIR dataset. The results demonstrate significant improvement on both reverberated fake speech and original samples, reducing DF task EER to 2.13%., Comment: 7 pages, to be presented at SLT 2024

Robotic manipulators are widely used in various industries for complex and repetitive tasks. However, they remain vulnerable to unexpected hardware failures. In this study, we address the challenge of enabling a robotic manipulator to complete tasks despite joint malfunctions. Specifically, we develop a reinforcement learning (RL) framework to adaptively compensate for a non-functional joint during task execution. Our experimental platform is the Franka robot with 7 degrees of freedom (DOFs). We formulate the problem as a partially observable Markov decision process (POMDP), where the robot is trained under various joint failure conditions and tested in both seen and unseen scenarios. We consider scenarios where a joint is permanently broken and where it functions intermittently. Additionally, we demonstrate the effectiveness of our approach by comparing it with traditional inverse kinematics-based control methods. The results show that the RL algorithm enables the robot to successfully complete tasks even with joint failures, achieving a high success rate with an average rate of 93.6%. This showcases its robustness and adaptability. Our findings highlight the potential of RL to enhance the resilience and reliability of robotic systems, making them better suited for unpredictable environments. All related codes and models are published online., Comment: 15 pages

Multilingual automatic speech recognition (ASR) in the medical domain serves as a foundational task for various downstream applications such as speech translation, spoken language understanding, and voice-activated assistants. This technology enhances patient care by enabling efficient communication across language barriers, alleviating specialized workforce shortages, and facilitating improved diagnosis and treatment, particularly during pandemics. In this work, we introduce MultiMed, a collection of small-to-large end-to-end ASR models for the medical domain, spanning five languages: Vietnamese, English, German, French, and Mandarin Chinese, together with the corresponding real-world ASR dataset. To our best knowledge, MultiMed stands as the largest and the first multilingual medical ASR dataset, in terms of total duration, number of speakers, diversity of diseases, recording conditions, speaker roles, unique medical terms, accents, and ICD-10 codes. Secondly, we establish the empirical baselines, present the first reproducible study of multilinguality in medical ASR, conduct a layer-wise ablation study for end-to-end ASR training, and provide the first linguistic analysis for multilingual medical ASR. All code, data, and models are available online https://github.com/leduckhai/MultiMed/tree/master/MultiMed, Comment: Preprint

Diffusion models (DMs) are advanced deep learning models that achieved state-of-the-art capability on a wide range of generative tasks. However, recent studies have shown their vulnerability regarding backdoor attacks, in which backdoored DMs consistently generate a designated result (e.g., a harmful image) called backdoor target when the models' input contains a backdoor trigger. Although various backdoor techniques have been investigated to attack DMs, defense methods against these threats are still limited and underexplored, especially in inverting the backdoor trigger. In this paper, we introduce PureDiffusion, a novel backdoor defense framework that can efficiently detect backdoor attacks by inverting backdoor triggers embedded in DMs. Our extensive experiments on various trigger-target pairs show that PureDiffusion outperforms existing defense methods with a large gap in terms of fidelity (i.e., how much the inverted trigger resembles the original trigger) and backdoor success rate (i.e., the rate that the inverted trigger leads to the corresponding backdoor target). Notably, in certain cases, backdoor triggers inverted by PureDiffusion even achieve higher attack success rate than the original triggers.

d/Deaf and hearing song-signers become prevalent on video-sharing platforms, but translating songs into sign language remains cumbersome and inaccessible. Our formative study revealed the challenges song-signers face, including semantic, syntactic, expressive, and rhythmic considerations in translations. We present ELMI, an accessible song-signing tool that assists in translating lyrics into sign language. ELMI enables users to edit glosses line-by-line, with real-time synced lyric highlighting and music video snippets. Users can also chat with a large language model-driven AI to discuss meaning, glossing, emoting, and timing. Through an exploratory study with 13 song-signers, we examined how ELMI facilitates their workflows and how song-signers leverage and receive an LLM-driven chat for translation. Participants successfully adopted ELMI to song-signing, with active discussions on the fly. They also reported improved confidence and independence in their translations, finding ELMI encouraging, constructive, and informative. We discuss design implications for leveraging LLMs in culturally sensitive song-signing translations., Comment: 18 pages excluding reference and appendix

In this paper we investigate a construction of scattering for wave-type equations with singular potentials on the whole space $\mathbb{R}^n$ in a framework of weak-$L^p$ spaces. First, we use an Yamazaki-type estimate for wave groups on Lorentz spaces and fixed point arguments to prove the global well-posedness for wave-type equations on weak-$L^p$ spaces. Then, we provide a corresponding scattering results in such singular framework. Finally, we use also the dispersive estimates to establish the polynomial stability and improve the decay of scattering., Comment: 15 pages

Temperate exoplanets between the sizes of Earth and Neptune, known as "sub-Neptunes", have emerged as intriguing targets for astrobiology. It is unknown whether these planets resemble Earth-like terrestrial worlds with a habitable surface, Neptune-like giant planets with deep atmospheres and no habitable surface, or something exotic in between. Recent JWST transmission spectroscopy observations of the canonical sub-Neptune K2-18 b revealed ~1% CH4, ~1% CO2, and a non-detection of CO in the atmosphere. While previous studies have proposed that the observed atmospheric composition could help constrain the lower atmosphere conditions and determine the interior structure of sub-Neptunes like K2-18 b, the possible interactions between the atmosphere and a hot, supercritical water ocean at its base remain unexplored. In this work, we investigate whether a global supercritical water ocean, resembling a planetary-scale hydrothermal system, can explain these observations on K2-18 b-like sub-Neptunes through equilibrium aqueous geochemical calculations. We find that the observed atmospheric CH4/CO2 ratio implies a minimum ocean temperature of ~715 K, whereas the corresponding CO/CO2 ratio allows ocean temperatures up to ~1060 K. These results indicate that a global supercritical water ocean on K2-18 b is plausible. While life cannot survive in this ocean, this work represents the first step towards understanding how a global supercritical water ocean may influence observable atmospheric characteristics on volatile-rich sub-Neptunes. Future observations with better constrained NH3 and CO mixing ratios could further help distinguish between possible interior compositions of K2-18 b., Comment: 15 pages, 5 figures, 1 table

Negation is a fundamental linguistic concept used by humans to convey information that they do not desire. Despite this, there has been minimal research specifically focused on negation within vision-language tasks. This lack of research means that vision-language models (VLMs) may struggle to understand negation, implying that they struggle to provide accurate results. One barrier to achieving human-level intelligence is the lack of a standard collection by which research into negation can be evaluated. This paper presents the first large-scale dataset, Negative Instruction (NeIn), for studying negation within the vision-language domain. Our dataset comprises 530,694 quadruples, i.e., source image, original caption, negative sentence, and target image in total, including 495,694 queries for training and 35,000 queries for benchmarking across multiple vision-language tasks. Specifically, we automatically generate NeIn based on a large, existing vision-language dataset, MS-COCO, via two steps: generation and filtering. During the generation phase, we leverage two VLMs, BLIP and MagicBrush, to generate the target image and a negative clause that expresses the content of the source image. In the subsequent filtering phase, we apply BLIP to remove erroneous samples. Additionally, we introduce an evaluation protocol for negation understanding of image editing models. Extensive experiments using our dataset across multiple VLMs for instruction-based image editing tasks demonstrate that even recent state-of-the-art VLMs struggle to understand negative queries. The project page is: https://tanbuinhat.github.io/NeIn/

We present a computational explainability approach for human comparison tasks, using Alignment Importance Score (AIS) heatmaps derived from deep-vision models. The AIS reflects a feature-map's unique contribution to the alignment between Deep Neural Network's (DNN) representational geometry and that of humans. We first validate the AIS by showing that prediction of out-of-sample human similarity judgments is improved when constructing representations using only higher-scoring AIS feature maps identified from a training set. We then compute image-specific heatmaps that visually indicate the areas that correspond to feature-maps with higher AIS scores. These maps provide an intuitive explanation of which image areas are more important when it is compared to other images in a cohort. We observe a correspondence between these heatmaps and saliency maps produced by a gaze-prediction model. However, in some cases, meaningful differences emerge, as the dimensions relevant for comparison are not necessarily the most visually salient. To conclude, Alignment Importance improves prediction of human similarity judgments from DNN embeddings, and provides interpretable insights into the relevant information in image space.

Previous menstrual health literature highlights a variety of signals not included in existing menstrual trackers because they are either difficult to gather or are not typically associated with menstrual health. Since it has become increasingly convenient to collect biomarkers through wearables and other consumer-grade devices, our work examines how people incorporate unconventional signals (e.g., blood glucose levels, heart rate) into their understanding of menstrual health. In this paper, we describe a three-month-long study on fifty participants' experiences as they tracked their health using physiological sensors and daily diaries. We analyzed their experiences with both conventional and unconventional menstrual health signals through surveys and interviews conducted throughout the study. We delve into the various aspects of menstrual health that participants sought to affirm using unconventional signals, explore how these signals influenced their daily behaviors, and examine how multimodal menstrual tracking expanded their scope of menstrual health. Finally, we provide design recommendations for future multimodal menstrual trackers., Comment: 25 pages, 4 figures, 2 tables. The paper was accepted by IMWUT/Ubicomp 2024

Hidden Markov Models (HMM) model a sequence of observations that are dependent on a hidden (or latent) state that follow a Markov chain. These models are widely used in diverse fields including ecology, speech recognition, and genetics.Parameter estimation in HMM is typically performed using the Baum-Welch algorithm, a special case of the Expectation-Maximisation (EM) algorithm. While this method guarantee the convergence to a local maximum, its convergence rates is usually slow.Alternative methods, such as the direct maximisation of the likelihood using quasi-Newton methods (such as L-BFGS-B) can offer faster convergence but can be more complicated to implement due to challenges to deal with the presence of bounds on the space of parameters.We propose a novel hybrid algorithm, QNEM, that combines the Baum-Welch and the quasi-Newton algorithms. QNEM aims to leverage the strength of both algorithms by switching from one method to the other based on the convexity of the likelihood function.We conducted a comparative analysis between QNEM, the Baum-Welch algorithm, an EM acceleration algorithm called SQUAREM (Varadhan, 2008, Scand J Statist), and the L-BFGS-B quasi-Newton method by applying these algorithms to four examples built on different models. We estimated the parameters of each model using the different algorithms and evaluated their performances.Our results show that the best-performing algorithm depends on the model considered. QNEM performs well overall, always being faster or equivalent to L-BFGS-B. The Baum-Welch and SQUAREM algorithms are faster than the quasi-Newton and QNEM algorithms in certain scenarios with multiple optimum. In conclusion, QNEM offers a promising alternative to existing algorithms.

We examine the role of refractory organics as a major C carrier in the outer protosolar nebula and its implications for the compositions of large Kuiper belt objects (KBOs) and CI chondrites. By utilizing Rosetta measurements of refractory organics in comet 67P/Churyumov-Gerasimenko, we show that they would make up a large fraction of the protosolar C inventory in the KBO-forming region based on the current widely adopted solar abundances. However, this would free up too much O to form water ice, producing solid material that is not sufficiently rock-rich to explain the uncompressed density of the Pluto-Charon system and other large KBOs; the former has been argued as the most representative value we have for the bulk composition of large KBOs (Barr & Schawmb 2016, Bierson & Nimmo 2019). This inconsistency further highlights the solar abundances problem - an ongoing challenge in reconciling spectroscopically determined heavy element abundances with helioseismology constraints. By employing a new dataset from solar CNO neutrinos and solar wind measurements of C, N, and O, we show that the uncompressed density of the Pluto-Charon system can be reproduced over a wide range of scenarios. We show that a lack of sulfates in Ryugu and Bennu samples implies a lower amount of water ice initially accreted into CI chondrite parent bodies than previously thought. These data are found to be consistent with the solar C/O ratio implied by the new dataset. Our predictions can be tested by future neutrino, helioseismology, and cosmochemical measurements., Comment: 32 pages, 10 figures, 3 tables, accepted for publication in ApJ

Recent advancements in deep learning have significantly improved visual quality inspection and predictive maintenance within industrial settings. However, deploying these technologies on low-resource edge devices poses substantial challenges due to their high computational demands and the inherent complexity of Explainable AI (XAI) methods. This paper addresses these challenges by introducing a novel XAI-integrated Visual Quality Inspection framework that optimizes the deployment of semantic segmentation models on low-resource edge devices. Our framework incorporates XAI and the Large Vision Language Model to deliver human-centered interpretability through visual and textual explanations to end-users. This is crucial for end-user trust and model interpretability. We outline a comprehensive methodology consisting of six fundamental modules: base model fine-tuning, XAI-based explanation generation, evaluation of XAI approaches, XAI-guided data augmentation, development of an edge-compatible model, and the generation of understandable visual and textual explanations. Through XAI-guided data augmentation, the enhanced model incorporating domain expert knowledge with visual and textual explanations is successfully deployed on mobile devices to support end-users in real-world scenarios. Experimental results showcase the effectiveness of the proposed framework, with the mobile model achieving competitive accuracy while significantly reducing model size. This approach paves the way for the broader adoption of reliable and interpretable AI tools in critical industrial applications, where decisions must be both rapid and justifiable. Our code for this work can be found at https://github.com/Analytics-Everywhere-Lab/vqixai., Comment: 29 pages, preprint submitted to Information Fusion journal

Scene graphs have been proven to be useful for various scene understanding tasks due to their compact and explicit nature. However, existing approaches often neglect the importance of maintaining the symmetry-preserving property when generating scene graphs from 3D point clouds. This oversight can diminish the accuracy and robustness of the resulting scene graphs, especially when handling noisy, multi-view 3D data. This work, to the best of our knowledge, is the first to implement an Equivariant Graph Neural Network in semantic scene graph generation from 3D point clouds for scene understanding. Our proposed method, ESGNN, outperforms existing state-of-the-art approaches, demonstrating a significant improvement in scene estimation with faster convergence. ESGNN demands low computational resources and is easy to implement from available frameworks, paving the way for real-time applications such as robotics and computer vision.

In this work we revisit the existence, uniqueness and exponential decay of some classes of mild solutions which are almost periodic (AP-), asymptotically almost periodic (AAP-) and pseudo almost periodic (PAP-) of the scalar Lin\'eard equation by employing the notion of Green function and Massera-type principle. First, by changing variable we convert this equation to a system of first order differential equations. Then, we transform the problem into a framework of an abstract parabolic evolution equation which associates with an evolution family equipped an exponential dichtonomy and the corresponding Green function is exponentially almost periodic. After that, we prove a Massera-type principle that the corresponding linear equation has a uniqueness AP-, AAP- and PAP- mild solution if the right hand side and the coefficient functions are AP-, AAP- and PAP- functions, respectively. The well-posedness of semilinear equation is proved by using fixed point arguments and the exponential decay of mild solutions are obtained by using Gronwall's inequality. Although our work revisits some previous works on well-posedness of the Lin\'eard equation on these type solutions but provide a difference view by using Green function and go farther on the aspects of asymptotic behaviour of solutions and the construction of abstract theory. Our abstract results can be also applied to other parabolic evolution equations., Comment: 20 pages

Creating soft-Coulomb-type (SC) molecular potential within single-active-electron approximation (SAE) is essential since it allows solving time-dependent Schr\"odinger equations with fewer computational resources compared to other multielectron methods. The current available SC potentials can accurately reproduce the energy of the highest occupied molecular orbital (HOMO), which is sufficient for analyzing nonlinear effects in laser-molecule interactions like high-order harmonic generation (HHG). However, recent discoveries of significant effects of deep-lying molecular orbitals call for more precise potentials to analyze them. In this study, we present a fast and accurate method based on machine learning to construct SC potentials that simultaneously reproduce various molecular features, including energies, symmetries, and dipole moments of HOMO, HOMO-1, and HOMO-2. We use this ML model to create SC SAE potentials of the HCN molecule and then comprehensively analyze the fingerprints of lower-lying orbitals in HHG spectra emitted during the H-CN stretching. Our findings reveal that HOMO-1 plays a role in forming the second HHG plateau. Additionally, as the H-C distance increases, the plateau structure and the smoothness of HHG spectra are altered due to the redistribution of orbital electron density. These results are in line with other experimental and theoretical studies. Lastly, the machine learning approach using deconvolution and convolution neural networks in the present study is so general that it can be applied to construct molecular potential for other molecules and molecular dynamic processes.